Professional Documents
Culture Documents
Improvement of Land Cover / Land Use Classification by Combination of Optical and Microwave Remote Sensing Data
Improvement of Land Cover / Land Use Classification by Combination of Optical and Microwave Remote Sensing Data
Abstract: Optical and microwave remote sensing data have been roughness, object density and their 3-D structure that are
widely used in land cover and land use classification. Thanks to very important complementary information to interpret
the spectral absorption characteristics of ground object in visible land use and land cover. Separate use of these data have
and near infrared region, optical data enables to extract different
brought many successful results in practice. However, the
land cover types according to their material composition like
water body, vegetation cover or bare land. On the other hand,
accuracy of the land use / land cover established by this
microwave sensor receives backscatter radiance which contains methodology still has some problems. One of the way to
information on surface roughness, object density and their 3-D improve accuracy of the land use / land cover classification
structure that are very important complementary information to is just combination of both optical and microwave data in
interpret land use and land cover. Separate use of these data have analysis. The ways of combination of these two data types
brought many successful results in practice. However, the are several. According to [2] one can fuse optical and
accuracy of the land use / land cover established by this microwave data by pixel, feature and decision based
methodology still has some problems. One of the way to improve approach. In pixel based fusion, the data are merged on a
accuracy of the land use / land cover classification is just
pixel-by-pixel basis. Feature based approach always merge
combination of both optical and microwave data in analysis. In
this paper for the research, the author used LANDSAT TM scene
the different data sources at the intermediate level. Each
127/45 acquired on October 21, 1992, JERS-1 SAR scene image from different sources is segmented and the
119/265 acquired on October 27, 1992 and aerial photographs segmented images are fused together. Decision based
taken on October 21, 1992. The study area has been selected in fusion, the outputs of each of the single source
Hanoi City and surrounding area, Vietnam. This is a flat interpretation are combined to create a new interpretation.
agricultural area with various land use types as water rice, Another concept is usage SAR data as complementary
secondary crops like maize, cassava, vegetables cultivation as information source for interpretation of optical imagery
cucumber, tomato etc. mixed with human settlement and some [1]. In this study, the author presents a decision based
manufacture facilities as brick and ceramic factories. The use of
combination of Landsat TM and JERS-1 SAR data for land
only optical or microwave data could result in misclassification
among some land use features as settlement and vegetables
cover mapping of Hanoi City and surrounding area. A
cultivation using frame stages. By combination of multitemporal comparison study of using only optical, single data SAR
JERS-1 SAR and TM data these errors have been eliminated so and multi-temporal SAR data for land cover mapping have
that accuracy of the final land use / land cover map has been been carried out. Finally a method for combination of
improved. The paper describes a methodology for data optical and microwave data has been proposed. Land cover
combination and presents results achieved by the proposed map which was compiled by the proposed method seems
approach. to be the best because it separates well many land cover
Keywords: Land cover, Classification, Optical and Microwave categories that can not be classified if only optical or
data, Remote sensing, Combination.
microwave data were used.
1. Introduction 2. Study Area
Land cover mapping has been one of activities of The study area is Hanoi City and surrounding area that
utilization of remote sensing data in earth sciences for a is located in north of Vietnam. Land cover of the study
long time. Both optical and microwave remote sensing area contains mainly categories as: urban, built-up, rural
data were intensively used for this purpose. Thanks to the human settlement, perennial and short term agricultural
spectral absorption characteristics of ground object in cultivation, rice crop, water bodies etc. The terrain is flat
visible and near infrared region, optical data enables to so there is no need of ortho-rectification of SAR data. Both
extract different land cover types according to their optical and SAR can be resample to the same spatial
material composition like water body, vegetation cover or resolution and overlaid each on the other. On figure 1 is
bare land. On the other hand, microwave sensor receives outline map of the study area.
backscatter radiance which contains information on surface
Fig. 1. Location of study area in North of Vietnam Fig. 2. Landsat TM false color composite of study area
3.2 Analysis of single date JERS-1 SAR data Fig. 4. Level sliced JERS-1 SAR image
3.3 Change extraction using multitemporal JERS-1
SAR data
Acknowledgement